Abstract
The double-phase-shift filtering method, which is based on the traditional pure-phase-shift filtering method, is a novel approach to harmonic elimination that can be applied to more complicated signals such as white noise and slip-sweep. Nonetheless, any type of phase-shift filtering method necessitates a relationship between the frequency of fundamental sweep and time, which may cost necessitate an enormous amount of human and physical resources to achieve inaccurate results with low efficiency. This paper combines deep learning with harmonic elimination to produce a double-phase-shift filtering method based on AR2U-Net, a type of U-Net with attention gates structure and recurrent residual blocks for improving accuracy and function while simplifying computational complexity. The input of the AR2U-Net structure in this paper is seismic data of slip-sweep signals in vibroseis, and the output is signal frequency variation with the time of the fundamental waves, which are required to eliminate the harmonic waves and adjacent signals using a double-phase-shift method to obtain the fundamental sweep. The training sets and test sets are formed by forward models, and a Log-Cosh loss function is used to monitor the process, during which the results of AR2U-Net and traditional U-Net are compared to demonstrate the eminent function of AR2U-Net. Following that, the outcomes’ Log-Cosh loss functions and accuracy are also compared to validate the conclusion. AR2U-Net, when applied to raw data and combined with the double-phase-shift method, tends to polish the filtering effects and is worth promoting.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Dongkwon, H., and Sunil, K., 2021, Application of machine learning method of data-driven deep learning model to predict well production rate in the shale gas reservoirs: Energies, 14(12), 3629–3629.
Han, W. X., Zhou, Y. T., and Chi, Y., 2018, Deep learning convolutional neural networks for random noise attenuation in seismic data: Geophysical Prospecting for Petroleum, 57(6), 862–869.
Hu, G., Hu, Z., Liu, J., et al., 2020, Seismic fault interpretation using deep learning-based semantic segmentation method: IEEE Geoscience and Remote Sensing Letters, 19, 1–5.
Kaur, H., Fomel, S., and Pham, N., 2020, Seismic ground-roll noise attenuation using deep learning: Geophysical Prospecting, 68(7), 2064–2077.
Kawulok, M., Benecki, P., Piechaczek, S., et al., 2020, Deep learning for multiple-image super-resolution: IEEE Geoscience and Remote Sensing Letters, 17(6), 1062–1066.
Lebedev, A. V., Beresnev, L. A., and Vermeer, P. L., 2006, Model parameters of the nonlinear stiffness of the vibrator-ground contact determined by inversion of vibrator accelerometer data: Geophysics, 71(3), H25–H32.
LeCun, Y., Boser, B., Denker, J. S., et al., 1989, Backpropagation applied to handwritten zip code recognition: Neural Computation, 1(4), 541–551.
Li, B. L., Wang, Y. C., Liu, X. Q., et al., 2021, Double-phase-shift filtering method for eliminating harmonic distortion in processing slip-sweep vibro-seismic signals: Oil Geophysics Prospecting, 56(2), 265–272.
Li, X. P., 1994, Decomposition of vibroseis data by multiple filter technique: 64th Ann. Internat. Mtg, Soc. Expl. Geophys., Expanded Abstracts, 13, 711–714.
Li, X. P., Sollner, W., and Hubral, P., 1995, Elimination of harmonic distortion in vibroseis data: Geophysics, 60(2), 503–516.
Ling, Y., Gao, J., Sun, D. S., et al., 2008, Vibroseis prospects and problems analysis in seismic exploration: Geophysical Prospecting for Petroleum, 47(5), 425–438.
Luo, R. Z., and Li, Y. Y., 2020, Random seismic noise attenuation based on RUnet convolutional neural network: Geophysical Prospecting for Petroleum, 59(1), 51–59.
Martin, J. E., and White, R. E., 1989, Two methods for continuous monitoring of harmonic distortion in vibroseis signals: Geophysical Prospecting, 37(7), 851–872.
Okaya, D. A., Karageorgi, E., and McEvilly, T. V., 1992, Removing vibrator-induced correlation artifacts by filtering in frequency-uncorrelated time space: Geophysics, 57(7), 916–926.
Qin, Y. S., and Wang, X. F., 2021, A joint segmentation method for optic disc and optic cup based on modified attention U-net: Computer Applications and Software, 38(3), 181–189.
Ras, P., Daly, M., Baeten, G., et al., 1999, Harmonic distortion in slip sweep records: 69th Ann. Internat. Mtg, Soc. Expl. Geophys., Expanded Abstracts, 609–612.
Ronneberger, O., Fischer, P., and Brox, T., 2015, Invited talk: U-Net convolutional networks for biomedical image segmentation: International Conference on Medical Image Computing and Computer Assisted Intervention, Cham, Springer, 234–241.
Rozemond, H. J., 1996, Slip sweep acquisition: 66th Ann. Internat. Mtg, Soc. Expl. Geophys., Expanded Abstracts, 15, 64–67.
Ruest, D. K., 1995, Vibrator force control: How simple can it get?: The Leading Edge, 14(11), 1129–1133.
Schrodt, J. K., 1987, Techniques for improving vibroseis data: Geophysics, 52(4), 469–482.
Si, X., and Yuan, Y., 2018, Random noise attenuation based on residual learning of deep convolutional neural network: 88th Ann. Internat. Mtg, Soc. Expl. Geophys., Expanded Abstracts, 1986–1990.
Wang, Y. Q., Lu, W. K., Liu, J. L., et al., 2019, Random seismic noise attenuation based on data augmentation and CNN: Chinese Journal of Geophysics, 62(1), 421–433.
Wu, X. M., Shi, Y. Z., FOMEL, S., et al., 2018, Convolutional neural networks for fault interpretation in seismic images: 88th Ann. Internat. Mtg, Soc. Expl. Geophys., Expanded Abstracts, 1946–1950.
Xiong, W., Ji, X., Ma, Y., et al., 2018, Seismic fault detection with convolutional neural network: Geophysics, 83(5), O97–O103.
Zhang, R. Q., Song, P., Liu, B. H., et al., 2020, Low-frequency swell noise suppression based on U-Net: Applied Geophysics, 17(3), 419–431.
Zhao, M., Chen, S., Fang, L., and David, A., 2019, Earthquake phase arrival auto-picking based on U-shaped convolutional neural network: Chinese Journal of Geophysics (in Chinese), 62(8), 3034–3042.
Zhou, D. W., Zhao, L. J., Duan, R., and Chai, X. L., 2019, Image super-resolution based on recursive residual networks: Acta Automatica Sinica, 45(6), 1157–1165.
This work was supported by the National Science and Technology Major Project of China (No. 2016ZX05003-003).
Author information
Authors and Affiliations
Corresponding author
Additional information
Li Bo-Lin graduated from China University of Geoscience in Beijing with a bachelor’s degree in Geophysics in 2018. He is a doctoral student in the School of Geophysics and Information Technology, China University of Geoscience in Beijing, and is mainly engaged in artificial intelligence-based signal processing and harmonic elimination in vibroseis. Mailing address: China University of Geoscience in Beijing, Beijing 100083, China.
This work was supported by the National Science and Technology Major Project of China (No. 2016ZX05003-003).
Rights and permissions
About this article
Cite this article
Li, BL., Wang, YC., Yuan, H. et al. Double-phase-shift filtering method for harmonic elimination based on AR2U-Net. Appl. Geophys. 19, 271–283 (2022). https://doi.org/10.1007/s11770-022-0932-8
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11770-022-0932-8